train

游雁

2023-05-16 3d9f094e9652d4b84894c6fd4eae39a4a753b0f0

 funasr/bin/train.py

@@ -16,6 +16,7 @@
from funasr.build_utils.build_scheduler import build_scheduler
from funasr.build_utils.build_trainer import build_trainer
from funasr.text.phoneme_tokenizer import g2p_choices
from funasr.torch_utils.load_pretrained_model import load_pretrained_model
from funasr.torch_utils.model_summary import model_summary
from funasr.torch_utils.pytorch_version import pytorch_cudnn_version
from funasr.torch_utils.set_all_random_seed import set_all_random_seed
@@ -333,12 +334,24 @@
        default="validation",
        help="dev dataset",
    )

    parser.add_argument(
        "--speed_perturb",
        type=float,
        nargs="+",
        default=None,
        help="speed perturb",
    )
    parser.add_argument(
        "--use_preprocessor",
        type=str2bool,
        default=True,
        help="Apply preprocessing to data or not",
    )
    parser.add_argument(
        "--embed_path",
        type=str,
        default=None,
        help="for model which requires embeds",
    )

    # optimization related
@@ -530,6 +543,18 @@
            else:
                yaml_no_alias_safe_dump(vars(args), f, indent=4, sort_keys=False)

    for p in args.init_param:
        logging.info(f"Loading pretrained params from {p}")
        load_pretrained_model(
            model=model,
            init_param=p,
            ignore_init_mismatch=args.ignore_init_mismatch,
            map_location=f"cuda:{torch.cuda.current_device()}"
            if args.ngpu > 0
            else "cpu",
            oss_bucket=args.oss_bucket,
        )

    # dataloader for training/validation
    train_dataloader, valid_dataloader = build_dataloader(args)